Job Description

Bangalore 2 3+ Years Full Time

We are looking for an innovative and highly skilled AI Application Engineer to join our team and develop state of-the-art enterprise-scale, public-facing AI applications. This role will provide you with the opportunity to shape the next generation of autonomous agent-based systems, focusing on performance, scalability, and cutting-edge technologies such as LLMs, embedding techniques, and agentic frameworks. As an AI Application Engineer, you will play a critical role in designing and implementing solutions that delight users while optimizing system performance. This position requires a combination of deep technical aptitude, creativity, and a commitment to excellence in application engineering.


Responsibilities:

Design, develop, and deploy enterprise-scale, public-facing AI applications. Implement advanced Retrieval Augmented Generation (RAG) architectures, including hybrid search and multi-vector retrieval. Build and optimize systems for token usage, response caching, and performance tuning. Develop and maintain autonomous agent frameworks using LangGraph or similar framework. Drive innovation in areas like embedding techniques, contextual compression, and multi-agent systems. Collaborate with cross-functional teams, including product managers, designers, and DevOps, to ensure robust and user-centric solutions. Troubleshoot complex technical challenges and mentor junior developers. Stay updated on the latest advancements in LLMs, agentic frameworks, and AI-driven application development.

Minimum Qualifications:

2-3 years of hands-on experience developing production-grade LLM applications. 3 to 5 years of overall software development experience. Minimum 1 year of experience in autonomous agent development using the LangGraph framework or similar.

Must-Have Skills:


1. Production-Grade LLM Development: Proven experience in developing and deploying large language model applications.


2. Autonomous Agent Development: Hands-on experience with frameworks like LangGraph for building autonomous agents.


3. Advanced RAG Architectures: Expertise in hybrid search, multi-vector retrieval, and contextual compression.


4. Prompt Engineering and Vector Search Optimization: Proficiency in crafting effective prompts and optimizing vector searches.


5. Performance Tuning and Token Optimization: Strong understanding of response caching and techniques to optimize token usage.